Hi, I’m Satyam! 🙌

I’m a Master’s student in Data Science at Indiana University, Bloomington. My interests lie at the interface of 3D Computer Vision and Language Models, focusing on Neural Scene Representations and 3D Scene Understanding. I’m especially excited about combining deep learning with graphics pipelines for photorealistic rendering of general dynamic scenes.

Currently I am working as a Machine Learning Research Assistant at the Cyberinfrastructure for Network Science Center (CNS), where I am collaborating with Dr. Katy Börner on a scalable computer vision pipeline for spatial biology. Along with developing reliable cell-segmentation and annotation workflows using models such as SAM and DeepCell, I am also focusing on the 3D nature of the underlying imagery. A large part of my work involves exploring volumetric representations, spatial embeddings, and interactive visualization techniques that make high-dimensional biological structures easier to interpret. The project has become a blend of deep learning, data engineering, and 3D visualization, and it continues to shape how I think about building systems that connect complex data with intuitive spatial understanding.

Previously, I spent a year as a researcher at Jio Institute, collaborating with Dr. Sudipta Roy on self-supervised learning for ultrasound (USG) cyst localization. My inclination toward research developed during my undergraduate internships at Indian Statistical Institute, Kolkata, under the guidance of Dr. Pradipta Maji, and at KJSCE, where I worked with Dr. Jagannath Nirmal on marine environmental monitoring using computer vision.

Outside of research, you’ll find me on the soccer field or deep into a science fiction movies (strictly no drama, real life already covers that genre). I have a soft spot for bold ideas, messy prototypes, and those problems that sneak into your head at 2 a.m. and have you sketching equations on whatever paper’s nearby.

You can find my full CV here and further information on my projects.

Research Interests:
                        • Vision Language Models
                        • Diffusion Models
                        • 3D Scene Understanding
                        • Agentic AI